Newer
Older
catch
committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
<?php
namespace Drupal\Component\Diff;
use Drupal\Component\Diff\Engine\HWLDFWordAccumulator;
use Drupal\Component\Utility\Unicode;
/**
* @todo document
* @private
* @subpackage DifferenceEngine
*/
class WordLevelDiff extends MappedDiff {
const MAX_LINE_LENGTH = 10000;
public function __construct($orig_lines, $closing_lines) {
list($orig_words, $orig_stripped) = $this->_split($orig_lines);
list($closing_words, $closing_stripped) = $this->_split($closing_lines);
parent::__construct($orig_words, $closing_words, $orig_stripped, $closing_stripped);
}
protected function _split($lines) {
$words = array();
$stripped = array();
$first = TRUE;
foreach ($lines as $line) {
// If the line is too long, just pretend the entire line is one big word
// This prevents resource exhaustion problems
if ( $first ) {
$first = FALSE;
}
else {
$words[] = "\n";
$stripped[] = "\n";
}
if (Unicode::strlen($line) > $this::MAX_LINE_LENGTH) {
$words[] = $line;
$stripped[] = $line;
}
else {
if (preg_match_all('/ ( [^\S\n]+ | [0-9_A-Za-z\x80-\xff]+ | . ) (?: (?!< \n) [^\S\n])? /xs', $line, $m)) {
$words = array_merge($words, $m[0]);
$stripped = array_merge($stripped, $m[1]);
}
}
}
return array($words, $stripped);
}
public function orig() {
$orig = new HWLDFWordAccumulator();
foreach ($this->edits as $edit) {
if ($edit->type == 'copy') {
$orig->addWords($edit->orig);
}
elseif ($edit->orig) {
$orig->addWords($edit->orig, 'mark');
}
}
$lines = $orig->getLines();
return $lines;
}
public function closing() {
$closing = new HWLDFWordAccumulator();
foreach ($this->edits as $edit) {
if ($edit->type == 'copy') {
$closing->addWords($edit->closing);
}
elseif ($edit->closing) {
$closing->addWords($edit->closing, 'mark');
}
}
$lines = $closing->getLines();
return $lines;
}